tcai_active_inference

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden for behavioral disclosure. It specifies the tool returns telemetry data and lists the quantities. However, it does not explicitly state that the tool is read-only, non-destructive, or disclose any side effects, rate limits, or prerequisites. The technical nature implies a query operation, but the absence of explicit transparency statements is a gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise. It front-loads the key outputs and includes citations for authority. However, the heavy jargon and references may reduce readability for an AI agent. Every clause earns its place, but the density could be slightly detrimental to quick parsing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has no parameters and no output schema, the description must fully explain what it returns. It does so comprehensively by listing all the core telemetry quantities: F, G(π) decomposed, task quality, model entropy, and Dirichlet-learned action. This is complete for the tool's purpose, and no further context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has zero parameters with 100% coverage. The description adds meaning by detailing what the tool returns, which is helpful for interpreting the output. Since there are no parameters to document, the baseline score of 4 is appropriate, and the description provides value beyond the schema by explaining the returned quantities.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides 'Active-inference core telemetry' listing specific quantities (F, G(π), task quality, etc.). It distinguishes itself from sibling tools by emphasizing it contains the 'principled quantity the halting criterion thresholds on' rather than heuristic correlates. The verb is implicit but the resource and scope are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for obtaining the genuine variational free energy and expected free energy used for halting decisions, contrasting with heuristic correlates. However, it does not explicitly state when to use this tool versus alternatives like tcai_metrics or tcai_convergence, nor does it provide explicit when-not-to-use guidance. The usage context is suggested but not fully delineated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.